Differentially Private Multi-Armed Bandits in the Shuffle Model

06/05/2021
by   Jay Tenenbaum, et al.
0

We give an (ε,δ)-differentially private algorithm for the multi-armed bandit (MAB) problem in the shuffle model with a distribution-dependent regret of O((∑_a∈ [k]:Δ_a>0log T/Δ_a)+k√(log1/δ)log T/ε), and a distribution-independent regret of O(√(kTlog T)+k√(log1/δ)log T/ε), where T is the number of rounds, Δ_a is the suboptimality gap of the arm a, and k is the total number of arms. Our upper bound almost matches the regret of the best known algorithms for the centralized model, and significantly outperforms the best known algorithm in the local model.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/11/2019

Batched Multi-Armed Bandits with Optimal Regret

We present a simple and efficient algorithm for the batched stochastic m...
research
11/27/2015

Algorithms for Differentially Private Multi-Armed Bandits

We present differentially private algorithms for the stochastic Multi-Ar...
research
01/16/2017

Achieving Privacy in the Adversarial Multi-Armed Bandit

In this paper, we improve the previously best known regret bound to achi...
research
06/25/2019

Restless dependent bandits with fading memory

We study the stochastic multi-armed bandit problem in the case when the ...
research
12/22/2020

Projection-Free Bandit Optimization with Privacy Guarantees

We design differentially private algorithms for the bandit convex optimi...
research
05/22/2021

From Finite to Countable-Armed Bandits

We consider a stochastic bandit problem with countably many arms that be...
research
10/04/2022

ProtoBandit: Efficient Prototype Selection via Multi-Armed Bandits

In this work, we propose a multi-armed bandit based framework for identi...

Please sign up or login with your details

Forgot password? Click here to reset